agents

A command for keeping coding-agent instruction files synchronized from one master AGENTS.md file. It creates host-specific copies for tools such as Cursor, Windsurf, Cline, and Codex, then detects differences between them.

In plain words
What is it for?
Use it after changing AGENTS.md to regenerate listed copies, check for drift, and verify synchronization in CI with procoder check.
Why use it?
It removes the need to edit many agent rule files separately and catches when one copy no longer matches the master.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/azrtydxb/procoder/agents
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00279
Opus 5 $0.00012 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash cae5fd249672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.kilo/commands/agents.md · 25 lines

What it actually says

The user invoked /procoder:agents.

The command below is the procoder binary on PATH.

procoder serves every AI coding agent from one canonical AGENTS.md: rule-file hosts (Cursor, Windsurf, Cline, Kilo Code, Roo Code, Kiro, Antigravity, Qoder, Copilot editors, Codex) each get a byte-identical copy under their own path, and the gate blocks when any copy drifts.

  1. Run procoder agents. For each file it reports missing or DRIFTED, write the printed content to the printed path — the content is the master plus that host's frontmatter; do not edit it by hand.
  2. To change the rules themselves, edit AGENTS.md (the master), then run procoder agents again and rewrite every copy it lists. Never edit a copy directly — the next check flags it as drift.
  3. Finish with procoder check — the same drift rules ride the gate, so CI agrees with what you just verified.

The full host matrix (plugin manifests, hooks, install per host) is in the docs under "Every agent".

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 25 lines · 24 tokens per session scan A cae5fd249672

Subscribe to this mod's changes

agents is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 279 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.